forked from jfmwz/spark-admin
/
handlers.py
314 lines (291 loc) · 14.3 KB
/
handlers.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
from multiprocessing import Process
from sys import stderr
from threading import Thread
from tornado import gen
from utils import ssh
import os
#import spark_ec2
import subprocess
import sys
import time
import tornado.web
import utils
from slacker import adisp
from slacker import Slacker
from slacker.workers import ThreadWorker
instance_types = [
# General purpose
"m3.large",
"m3.xlarge",
"m3.2xlarge",
"m3.medium",
"m1.small",
"m1.medium",
"m1.large",
"m1.xlarge",
# Compute optimized
"c3.large",
"c3.xlarge",
"c3.2xlarge",
"c3.4xlarge",
"c3.8xlarge",
"c1.medium",
"c1.xlarge",
"cc2.8xlarge",
# Memory optimized
"m2.xlarge",
"m2.2xlarge",
"m2.4xlarge",
"cr1.8xlarge",
# Storage optimized
"i2.xlarge",
"i2.2xlarge",
"i2.4xlarge",
"i2.8xlarge",
"hs1.8xlarge",
"hi1.4xlarge",
# GPU instances
"g2.2xlarge",
"cg1.4xlarge",
# Micro instances
"t1.micro"]
installer_dir = "../Installer/"
class NewClusterHandler(tornado.web.RequestHandler):
def get(self):
try:
conn = utils.get_ec2_conn(self)
key_pairs = conn.get_all_key_pairs()
self.render('new_cluster.html', error_msg=None, key_pairs=key_pairs, instance_types=instance_types)
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
def post(self):
try:
cluster_name = self.get_argument("cluster_name", "")
if (cluster_name == ""):
return self.render('error.html', error_msg="Cluster name is empty!")
conn = utils.get_ec2_conn(self)
(master_nodes, slave_nodes, zoo_nodes) = utils.get_existing_cluster(conn, cluster_name)
if len(master_nodes) > 0:
return self.render('error.html', error_msg="Cluster name is already existed!")
num_slave = self.get_argument("num_slave", "2")
key_pair = self.get_argument("key_pair", "")
instance_type = self.get_argument("instance_type", "m3.large")
#master_instance_type = self.get_argument("master_instance_type", "m1.small")
#zone = self.get_argument("zone", "us-east-1e")
ebs_vol_size = self.get_argument("ebs_vol_size", "10")
#swap = self.get_argument("swap", "1024")
cluster_type = self.get_argument("cluster_type", "mesos")
elastic_ip = self.get_argument("elastic_ip", "")
(AWS_ACCESS_KEY, AWS_SECRET_KEY) = utils.get_aws_credentials()
os.environ['AWS_ACCESS_KEY_ID'] = AWS_ACCESS_KEY
os.environ['AWS_SECRET_ACCESS_KEY'] = AWS_SECRET_KEY
key_pair_file = os.getcwd() + "/keys/" + key_pair + ".pem"
command = [installer_dir+"launch-cluster.sh",
cluster_name,
num_slave,
"--elastic-ip", elastic_ip,
"--ssh-key", key_pair,
"--type", instance_type,
#"--zone", zone,
"--ebs", ebs_vol_size
]
print ("Running : " + ' '.join(command))
subprocess.Popen(command)
#save the (cluster_name, elastic_ip) to file
utils.set_elastic_ip(cluster_name, elastic_ip)
time.sleep(10)
self.redirect("/")
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
class HomeHandler(tornado.web.RequestHandler):
def get(self):
try:
conn = utils.get_ec2_conn(self)
(cluster_names, dict_masters, dict_slaves) = utils.detect_existing_clusters(conn)
self.render('home.html', error_msg=None, cluster_names=cluster_names, dict_masters=dict_masters, dict_slaves=dict_slaves)
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
class ClusterHandler(tornado.web.RequestHandler):
def get(self, cluster_name):
try:
conn = utils.get_ec2_conn(self)
(master_nodes, slave_nodes, zoo_nodes) = utils.get_existing_cluster(conn, cluster_name)
services = [
"mesos",
"ganglia",
"ephemeral_hdfs",
"pi",
"pa",
"gridftp",
"spark"
]
service_names = {
"mesos" : "Mesos",
"ganglia" : "Ganglia",
"ephemeral_hdfs" : "Ephemeral HDFS",
"pa" : "Adatao pAnalytics",
"pi" : "Adatao pInsights",
"gridftp" : "Grid FTP",
"spark" : "Spark (after adatao.connect)"}
service_ports = {
"mesos" : 5050,
"ganglia" : 5080,
"ephemeral_hdfs" : 50070,
"pa" : 7911,
"pi" : 8890,
"gridftp" : 5000,
"spark" : 30001}
service_links = {
"mesos" : "http://" + master_nodes[0].public_dns_name + ":5050",
"ganglia" : "http://" + master_nodes[0].public_dns_name + ":5080/ganglia",
"ephemeral_hdfs" : "http://" + master_nodes[0].public_dns_name + ":50070",
"pa" : "http://" + master_nodes[0].public_dns_name + ":7911",
"pi" : "http://" + master_nodes[0].public_dns_name + ":8890",
"gridftp" : "",
"spark" : "http://" + master_nodes[0].public_dns_name + ":30001"}
service_statuses = {}
if len(master_nodes) > 0:
dns = master_nodes[0].public_dns_name
for service in services:
port = service_ports[service]
service_statuses[service] = utils.isOpen(dns, port)
self.render('cluster.html', error_msg=None, cluster_name=cluster_name, master_nodes=master_nodes, slave_nodes=slave_nodes, services=services, service_names=service_names, service_statuses=service_statuses, service_links=service_links)
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
class AboutHandler(tornado.web.RequestHandler):
def get(self):
self.render('about.html')
class SettingsHandler(tornado.web.RequestHandler):
def get(self):
(AWS_ACCESS_KEY, AWS_SECRET_KEY) = utils.get_aws_credentials()
self.render('settings.html', AWS_ACCESS_KEY=AWS_ACCESS_KEY, AWS_SECRET_KEY=AWS_SECRET_KEY, error_code= -1)
def post(self):
AWS_ACCESS_KEY = self.get_argument("AWS_ACCESS_KEY", "")
AWS_SECRET_KEY = self.get_argument("AWS_SECRET_KEY", "")
if AWS_ACCESS_KEY == "" or AWS_SECRET_KEY == "":
error_code = 1
error_msg = "Please fill in both Access key and Secret key!"
else:
error_code = 0
error_msg = "Update successfully!"
utils.save_aws_credentials(AWS_ACCESS_KEY, AWS_SECRET_KEY)
self.render('settings.html', AWS_ACCESS_KEY=AWS_ACCESS_KEY, AWS_SECRET_KEY=AWS_SECRET_KEY, error_code=error_code, error_msg=error_msg)
async_execute_sql = Slacker(utils.executeSql, ThreadWorker())
class SqlConsoleHandler(tornado.web.RequestHandler):
def get(self):
try:
self.render('sql_console.html', error_msg=None, code="show tables", server=self.get_argument("server", "localhost"), result="")
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
@tornado.web.asynchronous
@adisp.process
def post(self):
try:
server = self.get_argument("server", "localhost")
code = self.get_argument("code", "")
result = yield async_execute_sql(server, code)
self.render('sql_console.html', error_msg=None, code=code, server=server, result=result)
except Exception as e:
print >> stderr, (e)
self.render('error.html', error_msg=str(e))
async_ssh = Slacker(ssh, ThreadWorker())
class ActionHandler(tornado.web.RequestHandler):
@tornado.web.asynchronous
@adisp.process
def get(self):
try:
cluster_name = self.get_argument("cluster_name")
dns = self.get_argument("dns")
service = self.get_argument("service")
action = self.get_argument("action")
key_pair = self.get_argument("key_pair")
key_pair_file = os.getcwd() + "/keys/" + key_pair + ".pem"
# Execute action
if service == "mesos":
if action == "start":
yield async_ssh(key_pair_file, dns, "/root/spark-ec2/mesos/start-mesos")
elif action == "stop":
yield async_ssh(key_pair_file, dns, "/root/spark-ec2/mesos/stop-mesos")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "/root/spark-ec2/mesos/stop-mesos && /root/spark-ec2/mesos/start-mesos")
elif service == "shark":
if action == "start":
command = (("rsync --ignore-existing -rv -e 'ssh -o StrictHostKeyChecking=no -i %s' " +
"'%s/' 'root@%s:/root/shark-0.2/conf'") % (key_pair_file, 'deploy.shark', dns))
subprocess.check_call(command, shell=True)
yield async_ssh(key_pair_file, dns, "nohup ~/shark-0.2/bin/shark --service sharkserver >/dev/null &")
time.sleep(2) # Wait for Shark to restart
elif action == "stop":
yield async_ssh(key_pair_file, dns, "ps ax|grep shark.SharkServer|awk \"{print $1}\"|xargs kill")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "ps ax|grep shark.SharkServer|awk '{print $1}'|xargs kill && nohup ~/shark-0.2/bin/shark --service sharkserver >/dev/null &")
time.sleep(2) # Wait for Shark to restart
elif service == "ganglia":
if action == "start":
yield async_ssh(key_pair_file, dns, "/etc/init.d/gmetad start && /etc/init.d/httpd start")
elif action == "stop":
yield async_ssh(key_pair_file, dns, "/etc/init.d/gmetad stop && /etc/init.d/httpd stop")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "/etc/init.d/gmetad restart && /etc/init.d/httpd restart")
elif service == "pa":
if action == "start":
yield async_ssh(key_pair_file, dns, "pssh -v -h /root/spark-ec2/slaves -l root '/root/BigR/server/exe/start-rserve.sh' && /root/BigR/server/exe/start-pa-server.sh")
elif action == "stop":
yield async_ssh(key_pair_file, dns, "/root/BigR/server/exe/stop-pa-server.sh")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "/root/BigR/server/exe/stop-pa-server.sh && pssh -v -h /root/spark-ec2/slaves -l root '/root/BigR/server/exe/start-rserve.sh' && /root/BigR/server/exe/start-pa-server.sh")
elif service == "pi":
if action == "start":
yield async_ssh(key_pair_file, dns, "/root/pInsights/run-pInsights-server.sh")
elif action == "stop":
yield async_ssh(key_pair_file, dns, "pkill -f ipython")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "/root/pInsights/run-pInsights-server.sh")
elif service == "ephemeral_hdfs":
if action == "start":
yield async_ssh(key_pair_file, dns, "/root/ephemeral-hdfs/bin/start-dfs.sh")
elif action == "stop":
yield async_ssh(key_pair_file, dns, "/root/ephemeral-hdfs/bin/stop-dfs.sh")
elif action == "restart":
yield async_ssh(key_pair_file, dns, "/root/ephemeral-hdfs/bin/stop-dfs.sh && /root/ephemeral-hdfs/bin/start-dfs.sh")
elif service == "cluster":
if action == "start":
(AWS_ACCESS_KEY, AWS_SECRET_KEY) = utils.get_aws_credentials()
os.environ['AWS_ACCESS_KEY_ID'] = AWS_ACCESS_KEY
os.environ['AWS_SECRET_ACCESS_KEY'] = AWS_SECRET_KEY
# get the elastic-ip associated with cluster_name
elastic_ip = utils.get_elastic_ip(cluster_name)
command = [installer_dir+"start-cluster.sh",
cluster_name,
"--elastic-ip", elastic_ip]
print ("Running : " + ' '.join(command))
subprocess.Popen(command)
time.sleep(5)
self.redirect("/")
return
elif action == "stop":
command = [installer_dir+"stop-cluster.sh", cluster_name]
print ("Running : " + ' '.join(command))
subprocess.Popen(command)
time.sleep(3)
self.redirect("/")
return
elif action == "terminate":
command = [installer_dir+"terminate-cluster.sh", cluster_name]
print ("Running : " + ' '.join(command))
subprocess.Popen(command)
# delete the elastic-ip associated with cluster_name
utils.delete_elastic_ip(cluster_name)
time.sleep(3)
self.redirect("/")
return
time.sleep(1)
self.redirect("/cluster/" + cluster_name)
except Exception as e:
# print >> stderr, (e)
self.render('error.html', error_msg=str(e))